Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

set_curve_handle_xy

Set an independently editable outer Bezier handle to absolute 2D XY coordinates in millimeters, enabling precise pattern curve shaping with endpoint and handle semantics verified.

Instructions

Set one independently editable outer Bezier handle to absolute 2D XY in mm.

Select its pattern with md_select_pattern, set Edit Curve Point mode, and Fit Selected. Use a fresh scene_token and handle_ref from curve_handles and a unique request_id. The operation measures the current input mapping and verifies the native target, fixed endpoints, opposite handles and other 2D semantics before reporting success.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "pattern_uuid": "<pattern_uuid>",
      "handle_ref": "<handle_ref>",
      "x_mm": "<x_mm>",
      "y_mm": "<y_mm>",
      "scene_token": "<scene_token>"
    },
    "name": "set_curve_handle_xy"
  }
}

Input Schema

NameRequiredDescriptionDefault
x_mmYes
y_mmYes
handle_refYes
request_idNo
scene_tokenYes
pattern_uuidYes
tolerance_mmNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does meaningful work: it discloses that the operation measures the input mapping and verifies the native target, fixed endpoints, and opposite handles before reporting success, implying constraints can cause rejection. It also flags staleness and dedup requirements (fresh scene_token, unique request_id). It does not say what a failure returns or whether a partial application is rolled back.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well structured and front-loaded: the action comes first, then setup steps, then verification behavior. Every sentence contributes, though the middle sentence packs several distinct requirements (mode, Fit Selected, two token rules) into one line where a short list would read faster.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter mutation with no annotations, no output schema, and zero schema description coverage, the description is unusually informative about preconditions and verification but leaves tolerance_mm unexplained and gives no failure-mode or return-shape guidance. An agent could call it, but would be guessing about tolerance and error handling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must supply parameter meaning, and it covers handle_ref (from curve_handles), scene_token (must be fresh), request_id (must be unique), and x_mm/y_mm (absolute mm). tolerance_mm is never mentioned, and pattern_uuid is only obliquely implied by 'Select its pattern with md_select_pattern' rather than tied to the argument name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb (Set), a precisely scoped resource (one independently editable outer Bezier handle), and the exact value semantics (absolute 2D XY in mm). 'One' and 'outer' separate it from any bulk or inner-handle operation, and the mm unit disambiguates from screen-space siblings like canvas_gesture.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It spells out the prerequisite workflow — select the pattern via md_select_pattern, enter Edit Curve Point mode, Fit Selected — and names curve_handles as the source of handle_ref, which is real routing guidance an agent could not infer. It stops short of stating when NOT to use it or what to do if the scene is not in Edit Curve Point mode.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools